Papers › PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning

PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning

21 Nov 2022ICCV 2023 1arXiv:2211.11682archive 2025-07-28

Xiangyang Zhu, Renrui Zhang, Bowei He, Ziyu Guo, Ziyao Zeng, Zipeng Qin, Shanghang Zhang, Peng Gao

Large-scale pre-trained models have shown promising open-world performance for both vision and language tasks. However, their transferred capacity on 3D point clouds is still limited and only constrained to the classification task. In this paper, we first collaborate CLIP and GPT to be a unified 3D open-world learner, named as PointCLIP V2, which fully unleashes their potential for zero-shot 3D classification, segmentation, and detection. To better align 3D data with the pre-trained language knowledge, PointCLIP V2 contains two key designs. For the visual end, we prompt CLIP via a shape projection module to generate more realistic depth maps, narrowing the domain gap between projected point clouds with natural images. For the textual end, we prompt the GPT model to generate 3D-specific text as the input of CLIP's textual encoder. Without any training in 3D domains, our approach significantly surpasses PointCLIP by +42.90%, +40.44%, and +28.75% accuracy on three datasets for zero-shot 3D classification. On top of that, V2 can be extended to few-shot 3D classification, zero-shot 3D part segmentation, and 3D object detection in a simple manner, demonstrating our generalization ability for unified 3D open-world learning.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 8 ran (4 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yangyangyang127/pointclip_v2 officialmentioned in papermentioned on GitHubpytorchMITSyntology: 12 samples, 8 ran (4 instrument-failed) · 4 unverified report
zrrskywalker/pointclip mentioned on GitHubpytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
3ran · our draft was wrong
1ran; the contract check could not run
3ran
4unverified

Licence: 4 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from yangyangyang127/pointclip_v2. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

yangyangyang127/pointclip_v2 official repository 12 samples, 8 ran (4 instrument-failed) · 4 unverified
basic_clean in 217 papers zeroshot_cls/clip/simple_tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 98f385d847636a3e · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
cal_loss in 20 papers zeroshot_seg/util.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · c6c2758c0c2fa756 · report fixture: signature pred:Tensor/2/float, gold:Tensor/1/int, smoothing:bool/0/bool · returned Tensor · level recorded 2026-09-22
calculate_shape_IoU in 5 papers zeroshot_seg/util.py ran MIT (permissive) · d51a6e40c0aa5d4f · report fixture: signature pred_np:ndarray/2/int, seg_np:ndarray/2/int, label:Tensor/2/int, class_choice:bool/0/bool, eva:bool/0/bool · returned tuple · level recorded 2026-09-25
euler2mat in 21 papers zeroshot_seg/realistic_projection.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 140122b970061273 · report fixture: signature angle:Tensor/1/float · returned Tensor · level recorded 2026-09-22
getGaussianKernel2D zeroshot_seg/realistic_projection.py ran fingerprinted MIT (permissive) · 9b099a224dbca79d · report fixture: signature ksize:int/0/int, sigma:float/0/float · returned ndarray · level recorded 2026-09-25
get_pairs in 260 papers zeroshot_cls/clip/simple_tokenizer.py ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report fixture: signature word:tuple/1/str · returned set · level recorded 2026-09-22
points2grid zeroshot_seg/realistic_projection.py ran MIT (permissive) · 706ac9d3b62c54e8 · report fixture: signature points:Tensor/3/float, image_height:int/0/int, image_width:int/0/int, depth:int/0/int, device:str/0/str · returned tuple · level recorded 2026-09-25
whitespace_clean in 230 papers zeroshot_cls/clip/simple_tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9542161e9640b858 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
build_model in 469 papers zeroshot_cls/clip/model.py unverified MIT (permissive) here; the stored copy is pointer only · 69c02e4eb1c02a52 · report
build_model in 469 papers zeroshot_seg/clip/model.py unverified MIT (permissive) · e475fd539a310ed2 · report
load in 392 papers zeroshot_cls/clip/clip.py unverified MIT (permissive) · fbf8c0143d9c48e3 · report
load_data_partseg in 5 papers zeroshot_seg/data.py unverified MIT (permissive) · 6ac515bebb5bb563 · report

Tasks

3D Classification3D Object Detection3D Open-Vocabulary Instance Segmentation3D Part SegmentationClassificationDescriptiveObject DetectionOpen Vocabulary Object DetectionTraining-free 3D Part SegmentationTraining-free 3D Point Cloud ClassificationZero-Shot Transfer 3D Point Cloud ClassificationZero-shot 3D Point Cloud ClassificationZero-shot 3D classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Open-Vocabulary Instance Segmentation STPLS3D PointCLIPV2 AP50 03.1 #2 of 3 Archive leaderboard report
Training-free 3D Part Segmentation ShapeNet-Part PointCLIP V2 Need 3D Data? No #2 of 3 Archive leaderboard report
Training-free 3D Part Segmentation ShapeNet-Part PointCLIP V2 mIoU 48.4 #2 of 3 Archive leaderboard report
Training-free 3D Point Cloud Classification ModelNet40 PointCLIP V2 Accuracy (%) 64.2 #3 of 7 Archive leaderboard report
Training-free 3D Point Cloud Classification ModelNet40 PointCLIP V2 Need 3D Data? No #3 of 7 Archive leaderboard report
Training-free 3D Point Cloud Classification ScanObjectNN PointCLIP V2 Accuracy (%) 35.4 #3 of 6 Archive leaderboard report
Training-free 3D Point Cloud Classification ScanObjectNN PointCLIP V2 Need 3D Data? No #3 of 6 Archive leaderboard report
Zero-Shot Transfer 3D Point Cloud Classification ModelNet10 PointCLIP V2 Accuracy (%) 73.13 #2 of 4 Archive leaderboard report
Zero-Shot Transfer 3D Point Cloud Classification ModelNet40 PointCLIP V2 Accuracy (%) 64.22 #11 of 16 Archive leaderboard report
Zero-Shot Transfer 3D Point Cloud Classification ScanObjectNN PointCLIP V2 OBJ_BG Accuracy(%) 41.22 #7 of 10 Archive leaderboard report
Zero-Shot Transfer 3D Point Cloud Classification ScanObjectNN PointCLIP V2 OBJ_ONLY Accuracy(%) 50.09 #7 of 10 Archive leaderboard report
Zero-Shot Transfer 3D Point Cloud Classification ScanObjectNN PointCLIP V2 PB_T50_RS Accuracy (%) 35.36 #7 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ALIGNAdamAttentionAttention DropoutBPECLIPCosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPTLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections